View in EDS

A drone-based framework for coral habitat mapping via weakly supervised segmentation.

Saved in:
Bibliographic Details
Title: A drone-based framework for coral habitat mapping via weakly supervised segmentation.
Authors: Contini, Matteo1,2 (AUTHOR) matteo.contini@ifremer.fr, Illien, Victor1 (AUTHOR), Poulain, Sylvain3 (AUTHOR), Bernard, Serge4 (AUTHOR), Barde, Julien3 (AUTHOR), Bonhommeau, Sylvain1 (AUTHOR), Joly, Alexis2 (AUTHOR)
Source: Pattern Analysis & Applications. Jun2026, Vol. 29 Issue 2, p1-21. 21p.
Abstract: Obtaining pixel-level annotations over large spatial extents remains a major bottleneck for deploying machine learning in ecological applications. Here we present a multi-scale weakly supervised semantic segmentation (WSSS) framework that enables training high-resolution segmentation models from dense, classification-based outputs. Our method combines fine-scale, multi-label predictions from underwater imagery with broad-coverage aerial data. We convert these point-level classifications into coarse supervision masks that can be used to train a semantic segmentation model on Unmanned Aerial Vehicle (UAV) orthophotos. A second training step using the model’s own refined predictions is then used to further improve spatial accuracy without requiring additional annotations. We demonstrate the approach on coral reef imagery, enabling large-area segmentation of coral morphotypes and illustrating its flexibility in integrating new classes. The final model achieves 86.07% pixel accuracy and 52.23% mean Intersection over Union (mIoU) on manually annotated reef zones, demonstrating that accurate large-scale coral segmentation can be obtained without pixel-level annotations. By bridging image classification and segmentation across scales and modalities, this method provides an efficient solution for deploying segmentation models in settings where annotations are unavailable and opens opportunities for scalable, efficient monitoring in ecology and beyond. [ABSTRACT FROM AUTHOR]
Copyright of Pattern Analysis & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 193831239
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A drone-based framework for coral habitat mapping via weakly supervised segmentation.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Contini%2C+Matteo%22">Contini, Matteo</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> matteo.contini@ifremer.fr</i><br /><searchLink fieldCode="AR" term="%22Illien%2C+Victor%22">Illien, Victor</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Poulain%2C+Sylvain%22">Poulain, Sylvain</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Bernard%2C+Serge%22">Bernard, Serge</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Barde%2C+Julien%22">Barde, Julien</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Bonhommeau%2C+Sylvain%22">Bonhommeau, Sylvain</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Joly%2C+Alexis%22">Joly, Alexis</searchLink><relatesTo>2</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Pattern+Analysis+%26+Applications%22">Pattern Analysis & Applications</searchLink>. Jun2026, Vol. 29 Issue 2, p1-21. 21p.
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Obtaining pixel-level annotations over large spatial extents remains a major bottleneck for deploying machine learning in ecological applications. Here we present a multi-scale weakly supervised semantic segmentation (WSSS) framework that enables training high-resolution segmentation models from dense, classification-based outputs. Our method combines fine-scale, multi-label predictions from underwater imagery with broad-coverage aerial data. We convert these point-level classifications into coarse supervision masks that can be used to train a semantic segmentation model on Unmanned Aerial Vehicle (UAV) orthophotos. A second training step using the model’s own refined predictions is then used to further improve spatial accuracy without requiring additional annotations. We demonstrate the approach on coral reef imagery, enabling large-area segmentation of coral morphotypes and illustrating its flexibility in integrating new classes. The final model achieves 86.07% pixel accuracy and 52.23% mean Intersection over Union (mIoU) on manually annotated reef zones, demonstrating that accurate large-scale coral segmentation can be obtained without pixel-level annotations. By bridging image classification and segmentation across scales and modalities, this method provides an efficient solution for deploying segmentation models in settings where annotations are unavailable and opens opportunities for scalable, efficient monitoring in ecology and beyond. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Pattern Analysis & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193831239
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s10044-026-01682-3
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 21
        StartPage: 1
    Titles:
      – TitleFull: A drone-based framework for coral habitat mapping via weakly supervised segmentation.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Contini, Matteo
      – PersonEntity:
          Name:
            NameFull: Illien, Victor
      – PersonEntity:
          Name:
            NameFull: Poulain, Sylvain
      – PersonEntity:
          Name:
            NameFull: Bernard, Serge
      – PersonEntity:
          Name:
            NameFull: Barde, Julien
      – PersonEntity:
          Name:
            NameFull: Bonhommeau, Sylvain
      – PersonEntity:
          Name:
            NameFull: Joly, Alexis
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 14337541
          Numbering:
            – Type: volume
              Value: 29
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Pattern Analysis & Applications
              Type: main
ResultId 1